Skill/Plugin Backdoor
Install a backdoored skill or plugin that persists across agent restarts
Persistence · Stage 6
Establish persistent access surviving restarts and session changes
SKILL-FRONTMATTER
Embedding malicious instructions in skill or plugin metadata and description fields
Reproduced in a controlled lab environment (DVAA) with documented steps.
skill-backdoor-install
Reproductions in Damn Vulnerable AI Agent, the OpenA2A intentionally-broken agent for kill-chain validation.
AgentPwn coverage
An AgentPwn trap page produces a payload tagged with this technique class. Following the AgentPwn taxonomy of trap pages shows what an agent encounters.
Fake-package and malicious-MCP-server tiers instruct a backdoored skill/plugin install.
Evidence by source
Evidence timeline
HMA check SKILL-002 failed on fake-vulnerable-agent
HMA check SKILL-002 failed on fake-vulnerable-agent
HMA check SKILL-002 failed on fake-vulnerable-agent
HMA check SKILL-001 failed on opena2a/code-review-skill
HMA check SKILL-001 failed on opena2a/code-review-skill
HMA check SKILL-002 failed on fake-vulnerable-agent
HMA check SKILL-001 failed on damn-vulnerable-ai-agent
HMA check SKILL-001 failed on hackmyagent-release-test-vplv
Detection · HackMyAgent
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declaredDefense · OASB controls
How to cite
AI Agent Threat Matrix T-6004 (Skill/Plugin Backdoor). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-6004